© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21333
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iju
    -0.07
    pragma
    -0.06
    å·§
    -0.06
    éĢı
    -0.06
    ught
    -0.06
    icÃŃ
    -0.06
    icken
    -0.06
    clar
    -0.06
    olen
    -0.06
    æĽ¿
    -0.06
    POSITIVE LOGITS
    é¾Ļå±±
    0.08
    éĹĩ
    0.08
    neze
    0.08
    ç¼Ń
    0.07
    é¾Ļæ¹¾
    0.07
    atown
    0.07
    رخ
    0.07
    esian
    0.07
     Nguyen
    0.07
    éĻ¤æģ¶
    0.07
    Activations Density 0.003%

    No Known Activations